library(ggplot2)
library(plotly)
## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout
odiBowling <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Statistics\\odicareerbowling.csv")

df <- odiBowling[, 1:10]
head(df)
##                           Name Balls Maidens Runs Wickets Average
## 1            Aaron James Finch    73       0   59       2   29.50
## 2       Aavishkar Madhav Salvi   172       3  120       4   30.00
## 3             Abhimanyu Mithun   180       1  203       3   67.66
## 4         Abhishek Mohan Nayar    18       0   17       0      NA
## 5 Abraham Benjamin de Villiers   180       0  180       7   25.71
## 6           Adam Charles Voges   301       1  276       6   46.00
##   X5_Wicket_Hauls X10_Wicket_Hauls Strike_Rate Economy
## 1               0                0       36.50    4.84
## 2               0                0       43.00    4.18
## 3               0                0       60.00    6.76
## 4              NA               NA          NA    5.66
## 5               0                0       25.71    6.00
## 6               0                0       50.16    5.50
df <- na.omit(df)
head(df)
##                           Name Balls Maidens Runs Wickets Average
## 1            Aaron James Finch    73       0   59       2   29.50
## 2       Aavishkar Madhav Salvi   172       3  120       4   30.00
## 3             Abhimanyu Mithun   180       1  203       3   67.66
## 5 Abraham Benjamin de Villiers   180       0  180       7   25.71
## 6           Adam Charles Voges   301       1  276       6   46.00
## 7            Adam Fraser Milne  1463       5 1259      31   40.61
##   X5_Wicket_Hauls X10_Wicket_Hauls Strike_Rate Economy
## 1               0                0       36.50    4.84
## 2               0                0       43.00    4.18
## 3               0                0       60.00    6.76
## 5               0                0       25.71    6.00
## 6               0                0       50.16    5.50
## 7               0                0       47.19    5.16
summary(df)
##                            Name         Balls            Maidens      
##  Aaron James Finch           :  1   Min.   :    9.0   Min.   :  0.00  
##  Aavishkar Madhav Salvi      :  1   1st Qu.:  339.5   1st Qu.:  1.00  
##  Abhimanyu Mithun            :  1   Median : 1536.0   Median : 10.00  
##  Abraham Benjamin de Villiers:  1   Mean   : 2956.4   Mean   : 26.45  
##  Adam Charles Voges          :  1   3rd Qu.: 4274.5   3rd Qu.: 34.00  
##  Adam Fraser Milne           :  1   Max.   :18433.0   Max.   :308.00  
##  (Other)                     :205                                     
##       Runs          Wickets          Average       X5_Wicket_Hauls 
##  Min.   :   12   Min.   :  1.00   Min.   : 12.00   Min.   : 0.000  
##  1st Qu.:  336   1st Qu.:  8.00   1st Qu.: 28.05   1st Qu.: 0.000  
##  Median : 1344   Median : 40.00   Median : 33.44   Median : 1.000  
##  Mean   : 2355   Mean   : 76.33   Mean   : 38.34   Mean   : 1.976  
##  3rd Qu.: 3564   3rd Qu.:106.00   3rd Qu.: 38.73   3rd Qu.: 3.000  
##  Max.   :13575   Max.   :523.00   Max.   :172.00   Max.   :15.000  
##                                                                    
##  X10_Wicket_Hauls  Strike_Rate        Economy     
##  Min.   : 0.000   Min.   :  9.00   Min.   :2.850  
##  1st Qu.: 0.000   1st Qu.: 33.30   1st Qu.:4.740  
##  Median : 0.000   Median : 39.54   Median :5.080  
##  Mean   : 0.872   Mean   : 44.33   Mean   :5.149  
##  3rd Qu.: 1.000   3rd Qu.: 46.85   3rd Qu.:5.540  
##  Max.   :10.000   Max.   :156.00   Max.   :8.000  
## 
set.seed(20)

BWE <- df %>%
  select(2, 5, 10)

df2 <- df %>%
  select(3, 4, 8)

BWECluster <- kmeans(BWE, 5)

BWECluster$cluster <- as.factor(BWECluster$cluster)

plot_ly(BWE, x = ~Wickets, y = ~Economy, type = 'scatter',
        mode = 'markers', color = BWECluster$cluster,
        text = ~paste('Name: ', df$Name)) %>%
  layout(title = "Cluster of wickets & economy")